data(fallacies-fr): root4 audit — 5 REVERTs / 145 KEEP (Erreur de raisonnement) - #394
Merged
Merged
Conversation
…50c) 5 over-engineered cells reverted to baseline (Apr 2024) — pédagogique bloat without card-fit gain. 145 cells KEEP master (productive compressions, concept fixes, typography, tu→vous, orthographe). REVERTs: - 4.1.2.5 desc_fr 13w→20w bloat (deux torts font un droit) - 4.1.2.6 desc_fr 12w→19w bloat (sophisme du joueur) - 4.2.1.1 desc_fr 13w→20w bloat (transposition impropre) - 4.3.1.2.1 example_fr 24w→36w bloat narratif (équivalence morale) - 4.3.1.3 desc_fr 10w→15w bloat (acte de foi) Total Phase 4 audit complete: 7/7 L1 roots done. Generated by tmp/runs/build_decisions_4.py + apply_decisions.py. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
clusterManager-Myia
approved these changes
May 29, 2026
clusterManager-Myia
left a comment
Collaborator
There was a problem hiding this comment.
[Hermes] — APPROVED
PR: data(fallacies-fr): root4 audit — 5 REVERTs / 145 KEEP (Erreur de raisonnement)
SHA reviewed: c5ca176 (HEAD)
Security scan
✅ CLEAN — no hardcoded credentials in diff.
Review
Single-file CSV data revert: 5 desc_fr cells (PKs 713, 717, 728, 769, 770) restored to cleaner French descriptions in the Erreur de raisonnement section. No code, no logic changes. Targeted quality improvements (trimming bloat, improving precision).
Consistent with previously approved PRs #387-#393 (same audit pattern). No cross-repo impact.
This was referenced May 29, 2026
jsboige
added a commit
that referenced
this pull request
May 30, 2026
…t-5.5 (1281 cells, 61 PKs) (#397) Retraduit intégralement les 61 PKs AUDIT_FR vers 7 langues (EN/RU/PT/AR/ES/FA/ZH) × 3 champs (text/desc/example) = 1281 cellules, depuis le FR canonique post-audit (PRs #387-#394). Stratégie: blank-then-fill via prompt dédié non-drift. - Snapshot pré-blank: tmp/partb/fallacies_master_snapshot.csv (4,067,811 bytes) - Blank 1281 cellules (61 PKs × 21 cols) → cascade fired - Modèle: gpt-5.5 mono-tâche, SequentialChunks size=8, 28 chunks - Runtime: ~10:23, exit 0 - Output Target: 61/61 PKs full (21/21 cells), 0 partial, 0 empty → 100% fill - Surgical apply Target → master (1281 cells uniquement) Invariants vérifiés: - 1281/1281 cellules cibles remplies (100%) - Rows: 1409 (preserved) - Cols: 102 (preserved) - FR readonly: 0 drift sur 183 cellules FR (61 PKs × text_fr/desc_fr/example_fr) - Non-AUDIT_FR PKs (1348): 0 drift content-wise - Encoding: UTF-8 no-BOM, CRLF row terminators Nouveau prompt: PromptFallaciesFullRetranslation{User,Assistant}.txt - Non-drift, full-fill from FR canonical - ~21 UpdateRecord/record (7 langs × 3 champs) - Respecte invariants de style: EN impersonnel infinitif/gérondif, RU/PT/ES formel 2e pers plur miroir "Vous", AR/FA/ZH formel idiomatique, example_* 1ère pers narrative Config: DatasetUpdaterRootConfig.cs AUDIT_FR block → pointer DialogPrompts sur le nouveau prompt FullRetranslation (Enabled=false defensive maintenu). Fix taxonomique cascade-drift vs blank-fill (mémoire feedback enregistrée): le prompt cascade-drift juge "no drift" sur cellules vides (pas de baseline) → fill rate 45% sur Part A. Le nouveau prompt traite chaque cellule cible vide comme une traduction à émettre depuis FR canonique → 100% fill atteint. Refs: #335 (data-gate v0.9.0), #386 (Phase 4 Part B AUDIT_FR origin). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
jsboige
added a commit
that referenced
this pull request
May 30, 2026
…onfig (Enabled=false) Adds focused cascade config block "Fallacies AUDIT_FR cascade 7-lang gpt-5.5" to surface re-translation of 61 FR-audited PKs (PRs #387–#394) across EN/RU/PT/AR/ES/FA/ZH (text/desc/example × 7 langs = 21 cells per PK = 1281 cells). Strategy: blank-then-fill. - Operator blanks the 1281 cells (61 PKs × 21 cols) via tmp/partb_blank_audit_fr.py. - Config (SelectEmptyTargets=true) fills only those blanks. - Operator surgically patches the master Fallacies CSV with cascade output. Defensive: Enabled=false. Flip to true only at execution time. Differs from "Fallacies cascade multi-lang gpt-5.5" (line 1908) in: - FieldsToUpdate ADDS EN (existing block omits EN — caused this very re-cascade need). - SelectEmptyTargets=true (vs false) — chunker scopes to blanked cells only. - DivisionMode=SequentialChunks (PKs scattered, no hierarchical co-location). - TakeChunkNb=-1 (full run, not smoke). - MaxDegreeOfParallelismWebService=4 (vs 1). Builds clean (0 errors, only pre-existing warnings). Run via dotnet run after flipping Enabled. Refs ai-01 dispatch [TASK refinement 18:55] 2026-05-29; jsboige [GO 21:38]. Pairs with PR #396 (Part A salvage, 1,476 cells deterministic). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
jsboige
added a commit
that referenced
this pull request
May 30, 2026
…t-5.5 (1281 cells, 61 PKs) (#397) Retraduit intégralement les 61 PKs AUDIT_FR vers 7 langues (EN/RU/PT/AR/ES/FA/ZH) × 3 champs (text/desc/example) = 1281 cellules, depuis le FR canonique post-audit (PRs #387-#394). Stratégie: blank-then-fill via prompt dédié non-drift. - Snapshot pré-blank: tmp/partb/fallacies_master_snapshot.csv (4,067,811 bytes) - Blank 1281 cellules (61 PKs × 21 cols) → cascade fired - Modèle: gpt-5.5 mono-tâche, SequentialChunks size=8, 28 chunks - Runtime: ~10:23, exit 0 - Output Target: 61/61 PKs full (21/21 cells), 0 partial, 0 empty → 100% fill - Surgical apply Target → master (1281 cells uniquement) Invariants vérifiés: - 1281/1281 cellules cibles remplies (100%) - Rows: 1409 (preserved) - Cols: 102 (preserved) - FR readonly: 0 drift sur 183 cellules FR (61 PKs × text_fr/desc_fr/example_fr) - Non-AUDIT_FR PKs (1348): 0 drift content-wise - Encoding: UTF-8 no-BOM, CRLF row terminators Nouveau prompt: PromptFallaciesFullRetranslation{User,Assistant}.txt - Non-drift, full-fill from FR canonical - ~21 UpdateRecord/record (7 langs × 3 champs) - Respecte invariants de style: EN impersonnel infinitif/gérondif, RU/PT/ES formel 2e pers plur miroir "Vous", AR/FA/ZH formel idiomatique, example_* 1ère pers narrative Config: DatasetUpdaterRootConfig.cs AUDIT_FR block → pointer DialogPrompts sur le nouveau prompt FullRetranslation (Enabled=false defensive maintenu). Fix taxonomique cascade-drift vs blank-fill (mémoire feedback enregistrée): le prompt cascade-drift juge "no drift" sur cellules vides (pas de baseline) → fill rate 45% sur Part A. Le nouveau prompt traite chaque cellule cible vide comme une traduction à émettre depuis FR canonique → 100% fill atteint. Refs: #335 (data-gate v0.9.0), #386 (Phase 4 Part B AUDIT_FR origin). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
jsboige
added a commit
that referenced
this pull request
May 31, 2026
…Enabled=false) (#397) * feat(dataset-updater): Part B scaffolding — AUDIT_FR cascade 7-lang config (Enabled=false) Adds focused cascade config block "Fallacies AUDIT_FR cascade 7-lang gpt-5.5" to surface re-translation of 61 FR-audited PKs (PRs #387–#394) across EN/RU/PT/AR/ES/FA/ZH (text/desc/example × 7 langs = 21 cells per PK = 1281 cells). Strategy: blank-then-fill. - Operator blanks the 1281 cells (61 PKs × 21 cols) via tmp/partb_blank_audit_fr.py. - Config (SelectEmptyTargets=true) fills only those blanks. - Operator surgically patches the master Fallacies CSV with cascade output. Defensive: Enabled=false. Flip to true only at execution time. Differs from "Fallacies cascade multi-lang gpt-5.5" (line 1908) in: - FieldsToUpdate ADDS EN (existing block omits EN — caused this very re-cascade need). - SelectEmptyTargets=true (vs false) — chunker scopes to blanked cells only. - DivisionMode=SequentialChunks (PKs scattered, no hierarchical co-location). - TakeChunkNb=-1 (full run, not smoke). - MaxDegreeOfParallelismWebService=4 (vs 1). Builds clean (0 errors, only pre-existing warnings). Run via dotnet run after flipping Enabled. Refs ai-01 dispatch [TASK refinement 18:55] 2026-05-29; jsboige [GO 21:38]. Pairs with PR #396 (Part A salvage, 1,476 cells deterministic). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * data(fallacies): Part B AUDIT_FR cascade 7-lang full-retranslation gpt-5.5 (1281 cells, 61 PKs) (#397) Retraduit intégralement les 61 PKs AUDIT_FR vers 7 langues (EN/RU/PT/AR/ES/FA/ZH) × 3 champs (text/desc/example) = 1281 cellules, depuis le FR canonique post-audit (PRs #387-#394). Stratégie: blank-then-fill via prompt dédié non-drift. - Snapshot pré-blank: tmp/partb/fallacies_master_snapshot.csv (4,067,811 bytes) - Blank 1281 cellules (61 PKs × 21 cols) → cascade fired - Modèle: gpt-5.5 mono-tâche, SequentialChunks size=8, 28 chunks - Runtime: ~10:23, exit 0 - Output Target: 61/61 PKs full (21/21 cells), 0 partial, 0 empty → 100% fill - Surgical apply Target → master (1281 cells uniquement) Invariants vérifiés: - 1281/1281 cellules cibles remplies (100%) - Rows: 1409 (preserved) - Cols: 102 (preserved) - FR readonly: 0 drift sur 183 cellules FR (61 PKs × text_fr/desc_fr/example_fr) - Non-AUDIT_FR PKs (1348): 0 drift content-wise - Encoding: UTF-8 no-BOM, CRLF row terminators Nouveau prompt: PromptFallaciesFullRetranslation{User,Assistant}.txt - Non-drift, full-fill from FR canonical - ~21 UpdateRecord/record (7 langs × 3 champs) - Respecte invariants de style: EN impersonnel infinitif/gérondif, RU/PT/ES formel 2e pers plur miroir "Vous", AR/FA/ZH formel idiomatique, example_* 1ère pers narrative Config: DatasetUpdaterRootConfig.cs AUDIT_FR block → pointer DialogPrompts sur le nouveau prompt FullRetranslation (Enabled=false defensive maintenu). Fix taxonomique cascade-drift vs blank-fill (mémoire feedback enregistrée): le prompt cascade-drift juge "no drift" sur cellules vides (pas de baseline) → fill rate 45% sur Part A. Le nouveau prompt traite chaque cellule cible vide comme une traduction à émettre depuis FR canonique → 100% fill atteint. Refs: #335 (data-gate v0.9.0), #386 (Phase 4 Part B AUDIT_FR origin). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Septième et dernier audit cell-by-cell de la racine L1 4 (Erreur de raisonnement, 150 cellules régressées depuis avril 2024). Méthodologie validée jsboige : revert quand master a sur-pédagogisé sans gain de précision sur des cartes contraintes ~12-16w.
Total Phase 4 audit cell-by-cell complet : 7/7 roots (#388 root5, #389 root6, #390 root2, #391 root7, #392 root1, #393 root3, #394 root4).
REVERTs (5)
KEEPs notables (145)
Compressions productives:
Corrections concept/factuelles:
Tu→vous propagation systématique (4.1.2.2, 4.1.2.5.2, 4.1.2.5.1, 4.2.1.3, 4.2.1.3.1, 4.2.2.1.1, 4.2.3.4, 4.3.1.1.2.1, 4.3.2.1)
Typographie française (« », —, ', NBSP) appliquée systématiquement
Methodology
f38cfed9(April 2024) / REGRESSIONorigin/master/ HEADdesc_fr, ~25w pourexample_frtmp/runs/build_decisions_4.py+tmp/runs/apply_decisions.py(surgical binary patching)git diff --stat: 1 file, 5 insertions(+), 5 deletions(-) ✓Test Plan
Audit Status Phase 4
🤖 Generated with Claude Code